Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper names of places, names, and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, brands, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ounter
    -0.69
    etheless
    -0.64
     constitu
    -0.64
    äºĶ
    -0.63
     warranty
    -0.60
    ģĸ
    -0.60
     heel
    -0.60
    ĻĤ
    -0.60
     compromise
    -0.59
     similar
    -0.59
    POSITIVE LOGITS
    anooga
    0.90
    ingham
    0.87
    elia
    0.87
     Yards
    0.84
    love
    0.82
    enberg
    0.82
    leton
    0.81
    icut
    0.79
    entin
    0.79
    erton
    0.78
    Act Density 0.331%

    No Known Activations